深度学习 · foundation models论文趋势 2023–2026

ICML/NeurIPS 深度学习方向：foundation_models

统计范围：NeurIPS、ICLR、ICML、CVPR 四个会议，2023–2026 年，共 536 篇被归入该主题的论文。

主要结论

每年论文数

各会议论文数

按年份和会议统计

深度学习 · foundation models论文数，按年份和会议
年份NeurIPSICLRICMLCVPR合计
20236507072
20241920116209
202515653478
20262781357177

代表论文

按年份和会议均匀挑选，方便快速看到每一届的样貌

全部深度学习 · foundation models论文

年份全部2023202420252026
会议全部NeurIPSICLRICMLCVPR

共 536 篇，第 10 / 11 页

  1. NeurIPS 2024Transformers to SSMs: Distilling Quadratic Knowledge to Subquadratic Models
  2. NeurIPS 2024Understanding and Minimising Outlier Features in Transformer Training
  3. NeurIPS 2024Understanding Representation of Deep Equilibrium Models from Neural Collapse Perspective
  4. NeurIPS 2024Understanding the Differences in Foundation Models: Attention, State Space Models, and Recurrent Neural Networks
  5. NeurIPS 2024Understanding Transformer Reasoning Capabilities via Graph Algorithms
  6. NeurIPS 2024UNIT: Unifying Image and Text Recognition in One Vision Encoder
  7. NeurIPS 2024UniTS: A Unified Multi-Task Time Series Model
  8. NeurIPS 2024Universal Neural Functionals
  9. NeurIPS 2024Unveiling the Hidden Structure of Self-Attention via Kernel Principal Component Analysis
  10. NeurIPS 2024VB-LoRA: Extreme Parameter Efficient Fine-Tuning with Vector Banks
  11. NeurIPS 2024Vision Transformer Neural Architecture Search for Out-of-Distribution Generalization: Benchmark and Insights
  12. NeurIPS 2024xLSTM: Extended Long Short-Term Memory
  13. NeurIPS 2024YOLOv10: Real-Time End-to-End Object Detection
  14. NeurIPS 2024You Only Cache Once: Decoder-Decoder Architectures for Language Models
  15. ICML 2023$\pi$-Tuning: Transferring Multimodal Foundation Models with Optimal Multi-task Interpolation
  16. ICML 2023A Likelihood Approach to Nonparametric Estimation of a Singular Distribution Using Deep Generative Models
  17. ICML 2023CocktailSGD: Fine-tuning Foundation Models over 500Mbps Networks
  18. ICML 2023Improving Hyperparameter Learning under Approximate Inference in Gaussian Process Models
  19. ICML 2023Learning Unnormalized Statistical Models via Compositional Optimization
  20. ICML 2023Magneto: A Foundation Transformer
  21. ICML 2023On the Power of Foundation Models
  22. NeurIPS 20234M: Massively Multimodal Masked Modeling
  23. NeurIPS 2023A Pseudo-Semantic Loss for Autoregressive Models with Logical Constraints
  24. NeurIPS 2023ADGym: Design Choices for Deep Anomaly Detection
  25. NeurIPS 2023Agnostically Learning Single-Index Models using Omnipredictors
  26. NeurIPS 2023An Information-Theoretic Evaluation of Generative Models in Learning Multi-modal Distributions
  27. NeurIPS 2023BayesTune: Bayesian Sparse Deep Model Fine-tuning
  28. NeurIPS 2023Beyond Confidence: Reliable Models Should Also Consider Atypicality
  29. NeurIPS 2023BiMatting: Efficient Video Matting via Binarization
  30. NeurIPS 2023Birth of a Transformer: A Memory Viewpoint
  31. NeurIPS 2023Bridging the Domain Gap: Self-Supervised 3D Scene Understanding with Foundation Models
  32. NeurIPS 2023C-Eval: A Multi-Level Multi-Discipline Chinese Evaluation Suite for Foundation Models
  33. NeurIPS 2023CHAMMI: A benchmark for channel-adaptive models in microscopy imaging
  34. NeurIPS 2023Compositional Abilities Emerge Multiplicatively: Exploring Diffusion Models on a Synthetic Task
  35. NeurIPS 2023Contextually Affinitive Neighborhood Refinery for Deep Clustering
  36. NeurIPS 2023Differentiable Random Partition Models
  37. NeurIPS 2023Distributed Inference and Fine-tuning of Large Language Models Over The Internet
  38. NeurIPS 2023DreamSim: Learning New Dimensions of Human Visual Similarity using Synthetic Data
  39. NeurIPS 2023Efficient Equivariant Transfer Learning from Pretrained Models
  40. NeurIPS 2023EHRSHOT: An EHR Benchmark for Few-Shot Evaluation of Foundation Models
  41. NeurIPS 2023Energy Transformer
  42. NeurIPS 2023Estimating Riemannian Metric with Noise-Contaminated Intrinsic Distance
  43. NeurIPS 2023Evaluating Neuron Interpretation Methods of NLP Models
  44. NeurIPS 2023Every Parameter Matters: Ensuring the Convergence of Federated Learning with Dynamic Heterogeneous Models Reduction
  45. NeurIPS 2023Exploiting Connections between Lipschitz Structures for Certifiably Robust Deep Equilibrium Models
  46. NeurIPS 2023Foundation Model is Efficient Multimodal Multitask Model Selector
  47. NeurIPS 2023FreeMask: Synthetic Images with Dense Annotations Make Stronger Segmentation Models
  48. NeurIPS 2023Generalized Logit Adjustment: Calibrating Fine-tuned Models by Removing Label Bias in Foundation Models
  49. NeurIPS 2023Generating QM1B with PySCF$_{\text{IPU}}$
  50. NeurIPS 2023GEO-Bench: Toward Foundation Models for Earth Monitoring

在 Claude、Cursor 里直接问这个趋势

接上 Paperlist MCP 后，写综述、挑方向或准备投稿时，不用离开对话框就能拿到这页的数字：每年各会议的论文数、增长倍数、涨得最快的子方向和代表论文，AI 会按你的问题整理。

可以直接复制这句话问 AI

用 paperlist 查深度学习 · foundation models在 NeurIPS 2023–2026 的论文趋势，哪一年涨得最快？

AI 会调用的工具：get_topic_stats {"topic": "dl-foundation-models"}

两分钟接入 Paperlist MCP（Claude Code、Cursor、Codex、ChatGPT）

常见问题

2023–2026 年四大会议一共有多少篇深度学习 · foundation models论文？
共 536 篇，按年份分别是 2023 年 72 篇、2024 年 209 篇、2025 年 78 篇、2026 年 177 篇。
NeurIPS 2026 有多少篇深度学习 · foundation models论文？
NeurIPS 2026 有 27 篇深度学习 · foundation models论文，上一届是 15 篇。
ICLR 2026 有多少篇深度学习 · foundation models论文？
ICLR 2026 有 8 篇深度学习 · foundation models论文，上一届是 6 篇。
ICML 2026 有多少篇深度学习 · foundation models论文？
ICML 2026 有 135 篇深度学习 · foundation models论文，上一届是 53 篇。
CVPR 2026 有多少篇深度学习 · foundation models论文？
CVPR 2026 有 7 篇深度学习 · foundation models论文，上一届是 4 篇。
哪个会议的深度学习 · foundation models论文最多？
NeurIPS，2023–2026 年共 299 篇。

「深度学习」下的其他主题